
# !pip install git+https://github.com/alberanid/imdbpy
# !pip install pandas
# !pip install numpy
# !pip install matplotlib
# !pip install seaborn
# !pip install pandas_profiling --upgrade
# !pip install plotly
# !pip install wordcloud
# !pip install Flask


# Import Dataset
# Import File from Loacal Drive
# from google.colab import files
# data_to_load = files.upload()
# from google.colab import drive
# drive.mount('/content/drive')


import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
import collections
import plotly.express as px
import plotly.graph_objects as go
import nltk
import re
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from nltk.probability import FreqDist
from nltk.util import ngrams
from plotly.subplots import make_subplots
from plotly.offline import iplot, init_notebook_mode
from wordcloud import WordCloud, STOPWORDS
from pandas_profiling import ProfileReport
%matplotlib inline
warnings.filterwarnings("ignore")


nltk.download('all')

[nltk_data] Downloading collection 'all'
[nltk_data]    | 
[nltk_data]    | Downloading package abc to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package abc is already up-to-date!
[nltk_data]    | Downloading package alpino to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package alpino is already up-to-date!
[nltk_data]    | Downloading package biocreative_ppi to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package biocreative_ppi is already up-to-date!
[nltk_data]    | Downloading package brown to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package brown is already up-to-date!
[nltk_data]    | Downloading package brown_tei to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package brown_tei is already up-to-date!
[nltk_data]    | Downloading package cess_cat to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package cess_cat is already up-to-date!
[nltk_data]    | Downloading package cess_esp to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package cess_esp is already up-to-date!
[nltk_data]    | Downloading package chat80 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package chat80 is already up-to-date!
[nltk_data]    | Downloading package city_database to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package city_database is already up-to-date!
[nltk_data]    | Downloading package cmudict to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package cmudict is already up-to-date!
[nltk_data]    | Downloading package comparative_sentences to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package comparative_sentences is already up-to-
[nltk_data]    |       date!
[nltk_data]    | Downloading package comtrans to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package comtrans is already up-to-date!
[nltk_data]    | Downloading package conll2000 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package conll2000 is already up-to-date!
[nltk_data]    | Downloading package conll2002 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package conll2002 is already up-to-date!
[nltk_data]    | Downloading package conll2007 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package conll2007 is already up-to-date!
[nltk_data]    | Downloading package crubadan to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package crubadan is already up-to-date!
[nltk_data]    | Downloading package dependency_treebank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package dependency_treebank is already up-to-date!
[nltk_data]    | Downloading package dolch to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package dolch is already up-to-date!
[nltk_data]    | Downloading package europarl_raw to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package europarl_raw is already up-to-date!
[nltk_data]    | Downloading package floresta to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package floresta is already up-to-date!
[nltk_data]    | Downloading package framenet_v15 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package framenet_v15 is already up-to-date!
[nltk_data]    | Downloading package framenet_v17 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package framenet_v17 is already up-to-date!
[nltk_data]    | Downloading package gazetteers to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package gazetteers is already up-to-date!
[nltk_data]    | Downloading package genesis to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package genesis is already up-to-date!
[nltk_data]    | Downloading package gutenberg to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package gutenberg is already up-to-date!
[nltk_data]    | Downloading package ieer to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ieer is already up-to-date!
[nltk_data]    | Downloading package inaugural to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package inaugural is already up-to-date!
[nltk_data]    | Downloading package indian to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package indian is already up-to-date!
[nltk_data]    | Downloading package jeita to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package jeita is already up-to-date!
[nltk_data]    | Downloading package kimmo to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package kimmo is already up-to-date!
[nltk_data]    | Downloading package knbc to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package knbc is already up-to-date!
[nltk_data]    | Downloading package lin_thesaurus to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package lin_thesaurus is already up-to-date!
[nltk_data]    | Downloading package mac_morpho to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package mac_morpho is already up-to-date!
[nltk_data]    | Downloading package machado to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package machado is already up-to-date!
[nltk_data]    | Downloading package masc_tagged to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package masc_tagged is already up-to-date!
[nltk_data]    | Downloading package moses_sample to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package moses_sample is already up-to-date!
[nltk_data]    | Downloading package movie_reviews to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package movie_reviews is already up-to-date!
[nltk_data]    | Downloading package names to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package names is already up-to-date!
[nltk_data]    | Downloading package nombank.1.0 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package nombank.1.0 is already up-to-date!
[nltk_data]    | Downloading package nps_chat to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package nps_chat is already up-to-date!
[nltk_data]    | Downloading package omw to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package omw is already up-to-date!
[nltk_data]    | Downloading package opinion_lexicon to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package opinion_lexicon is already up-to-date!
[nltk_data]    | Downloading package paradigms to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package paradigms is already up-to-date!
[nltk_data]    | Downloading package pil to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package pil is already up-to-date!
[nltk_data]    | Downloading package pl196x to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package pl196x is already up-to-date!
[nltk_data]    | Downloading package ppattach to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ppattach is already up-to-date!
[nltk_data]    | Downloading package problem_reports to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package problem_reports is already up-to-date!
[nltk_data]    | Downloading package propbank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package propbank is already up-to-date!
[nltk_data]    | Downloading package ptb to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ptb is already up-to-date!
[nltk_data]    | Downloading package product_reviews_1 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package product_reviews_1 is already up-to-date!
[nltk_data]    | Downloading package product_reviews_2 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package product_reviews_2 is already up-to-date!
[nltk_data]    | Downloading package pros_cons to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package pros_cons is already up-to-date!
[nltk_data]    | Downloading package qc to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package qc is already up-to-date!
[nltk_data]    | Downloading package reuters to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package reuters is already up-to-date!
[nltk_data]    | Downloading package rte to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package rte is already up-to-date!
[nltk_data]    | Downloading package semcor to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package semcor is already up-to-date!
[nltk_data]    | Downloading package senseval to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package senseval is already up-to-date!
[nltk_data]    | Downloading package sentiwordnet to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sentiwordnet is already up-to-date!
[nltk_data]    | Downloading package sentence_polarity to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sentence_polarity is already up-to-date!
[nltk_data]    | Downloading package shakespeare to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package shakespeare is already up-to-date!
[nltk_data]    | Downloading package sinica_treebank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sinica_treebank is already up-to-date!
[nltk_data]    | Downloading package smultron to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package smultron is already up-to-date!
[nltk_data]    | Downloading package state_union to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package state_union is already up-to-date!
[nltk_data]    | Downloading package stopwords to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package stopwords is already up-to-date!
[nltk_data]    | Downloading package subjectivity to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package subjectivity is already up-to-date!
[nltk_data]    | Downloading package swadesh to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package swadesh is already up-to-date!
[nltk_data]    | Downloading package switchboard to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package switchboard is already up-to-date!
[nltk_data]    | Downloading package timit to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package timit is already up-to-date!
[nltk_data]    | Downloading package toolbox to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package toolbox is already up-to-date!
[nltk_data]    | Downloading package treebank to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package treebank is already up-to-date!
[nltk_data]    | Downloading package twitter_samples to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package twitter_samples is already up-to-date!
[nltk_data]    | Downloading package udhr to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package udhr is already up-to-date!
[nltk_data]    | Downloading package udhr2 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package udhr2 is already up-to-date!
[nltk_data]    | Downloading package unicode_samples to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package unicode_samples is already up-to-date!
[nltk_data]    | Downloading package universal_treebanks_v20 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package universal_treebanks_v20 is already up-to-
[nltk_data]    |       date!
[nltk_data]    | Downloading package verbnet to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package verbnet is already up-to-date!
[nltk_data]    | Downloading package verbnet3 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package verbnet3 is already up-to-date!
[nltk_data]    | Downloading package webtext to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package webtext is already up-to-date!
[nltk_data]    | Downloading package wordnet to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package wordnet is already up-to-date!
[nltk_data]    | Downloading package wordnet_ic to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package wordnet_ic is already up-to-date!
[nltk_data]    | Downloading package words to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package words is already up-to-date!
[nltk_data]    | Downloading package ycoe to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package ycoe is already up-to-date!
[nltk_data]    | Downloading package rslp to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package rslp is already up-to-date!
[nltk_data]    | Downloading package maxent_treebank_pos_tagger to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package maxent_treebank_pos_tagger is already up-
[nltk_data]    |       to-date!
[nltk_data]    | Downloading package universal_tagset to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package universal_tagset is already up-to-date!
[nltk_data]    | Downloading package maxent_ne_chunker to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package maxent_ne_chunker is already up-to-date!
[nltk_data]    | Downloading package punkt to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package punkt is already up-to-date!
[nltk_data]    | Downloading package book_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package book_grammars is already up-to-date!
[nltk_data]    | Downloading package sample_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package sample_grammars is already up-to-date!
[nltk_data]    | Downloading package spanish_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package spanish_grammars is already up-to-date!
[nltk_data]    | Downloading package basque_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package basque_grammars is already up-to-date!
[nltk_data]    | Downloading package large_grammars to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package large_grammars is already up-to-date!
[nltk_data]    | Downloading package tagsets to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package tagsets is already up-to-date!
[nltk_data]    | Downloading package snowball_data to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package snowball_data is already up-to-date!
[nltk_data]    | Downloading package bllip_wsj_no_aux to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package bllip_wsj_no_aux is already up-to-date!
[nltk_data]    | Downloading package word2vec_sample to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package word2vec_sample is already up-to-date!
[nltk_data]    | Downloading package panlex_swadesh to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package panlex_swadesh is already up-to-date!
[nltk_data]    | Downloading package mte_teip5 to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package mte_teip5 is already up-to-date!
[nltk_data]    | Downloading package averaged_perceptron_tagger to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package averaged_perceptron_tagger is already up-
[nltk_data]    |       to-date!
[nltk_data]    | Downloading package averaged_perceptron_tagger_ru to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package averaged_perceptron_tagger_ru is already
[nltk_data]    |       up-to-date!
[nltk_data]    | Downloading package perluniprops to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package perluniprops is already up-to-date!
[nltk_data]    | Downloading package nonbreaking_prefixes to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package nonbreaking_prefixes is already up-to-date!
[nltk_data]    | Downloading package vader_lexicon to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package vader_lexicon is already up-to-date!
[nltk_data]    | Downloading package porter_test to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package porter_test is already up-to-date!
[nltk_data]    | Downloading package wmt15_eval to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package wmt15_eval is already up-to-date!
[nltk_data]    | Downloading package mwa_ppdb to
[nltk_data]    |     C:\Users\pawan\AppData\Roaming\nltk_data...
[nltk_data]    |   Package mwa_ppdb is already up-to-date!
[nltk_data]    | 
[nltk_data]  Done downloading collection all

True


# path = '/content/drive/MyDrive/Files/'

path = 'C:\\Users\\pawan\\OneDrive\\Desktop\\ott\\Data\\'
 
df_tvshows = pd.read_csv(path + 'otttvshows.csv')
 
df_tvshows.head()


# profile = ProfileReport(df_tvshows)
# profile


def data_investigate(df):
    print('No of Rows : ', df.shape[0])
    print('No of Coloums : ', df.shape[1])
    print('**'*25)
    print('Colums Names : \n', df.columns)
    print('**'*25)
    print('Datatype of Columns : \n', df.dtypes)
    print('**'*25)
    print('Missing Values : ')
    c = df.isnull().sum()
    c = c[c > 0]
    print(c)
    print('**'*25)
    print('Missing vaules %age wise :\n')
    print((100*(df.isnull().sum()/len(df.index))))
    print('**'*25)
    print('Pictorial Representation : ')
    plt.figure(figsize = (10, 10))
    sns.heatmap(df.isnull(), yticklabels = False, cbar = False)
    plt.show()


data_investigate(df_tvshows)

No of Rows :  5432
No of Coloums :  20
**************************************************
Colums Names : 
 Index(['ID', 'Title', 'Year', 'Age', 'IMDb', 'Rotten Tomatoes', 'Directors',
       'Cast', 'Genres', 'Country', 'Language', 'Plotline', 'Runtime', 'Kind',
       'Seasons', 'Netflix', 'Hulu', 'Prime Video', 'Disney+', 'Type'],
      dtype='object')
**************************************************
Datatype of Columns : 
 ID                   int64
Title               object
Year                 int64
Age                 object
IMDb               float64
Rotten Tomatoes     object
Directors           object
Cast                object
Genres              object
Country             object
Language            object
Plotline            object
Runtime            float64
Kind                object
Seasons            float64
Netflix              int64
Hulu                 int64
Prime Video          int64
Disney+              int64
Type                 int64
dtype: object
**************************************************
Missing Values : 
Age                1954
IMDb                556
Rotten Tomatoes    4194
Directors          5158
Cast                486
Genres              323
Country             549
Language            638
Plotline           2493
Runtime            1410
Seasons             679
dtype: int64
**************************************************
Missing vaules %age wise :

ID                  0.000000
Title               0.000000
Year                0.000000
Age                35.972018
IMDb               10.235641
Rotten Tomatoes    77.209131
Directors          94.955817
Cast                8.946981
Genres              5.946244
Country            10.106775
Language           11.745214
Plotline           45.894698
Runtime            25.957290
Kind                0.000000
Seasons            12.500000
Netflix             0.000000
Hulu                0.000000
Prime Video         0.000000
Disney+             0.000000
Type                0.000000
dtype: float64
**************************************************
Pictorial Representation :


# ID
# df_tvshows = df_tvshows.drop(['ID'], axis = 1)
 
# Age
df_tvshows.loc[df_tvshows['Age'].isnull() & df_tvshows['Disney+'] == 1, "Age"] = '13'
# df_tvshows.fillna({'Age' : 18}, inplace = True)
df_tvshows.fillna({'Age' : 'NR'}, inplace = True)
df_tvshows['Age'].replace({'all': '0'}, inplace = True)
df_tvshows['Age'].replace({'7+': '7'}, inplace = True)
df_tvshows['Age'].replace({'13+': '13'}, inplace = True)
df_tvshows['Age'].replace({'16+': '16'}, inplace = True)
df_tvshows['Age'].replace({'18+': '18'}, inplace = True)
# df_tvshows['Age'] = df_tvshows['Age'].astype(int)
 
# IMDb
# df_tvshows.fillna({'IMDb' : df_tvshows['IMDb'].mean()}, inplace = True)
# df_tvshows.fillna({'IMDb' : df_tvshows['IMDb'].median()}, inplace = True)
df_tvshows.fillna({'IMDb' : "NA"}, inplace = True)
 
# Rotten Tomatoes
df_tvshows['Rotten Tomatoes'] = df_tvshows['Rotten Tomatoes'][df_tvshows['Rotten Tomatoes'].notnull()].str.replace('%', '').astype(int)
# df_tvshows['Rotten Tomatoes'] = df_tvshows['Rotten Tomatoes'][df_tvshows['Rotten Tomatoes'].notnull()].astype(int)
# df_tvshows.fillna({'Rotten Tomatoes' : df_tvshows['Rotten Tomatoes'].mean()}, inplace = True)
# df_tvshows.fillna({'Rotten Tomatoes' : df_tvshows['Rotten Tomatoes'].median()}, inplace = True)
# df_tvshows['Rotten Tomatoes'] = df_tvshows['Rotten Tomatoes'].astype(int)
df_tvshows.fillna({'Rotten Tomatoes' : "NA"}, inplace = True)
 
# Directors
# df_tvshows = df_tvshows.drop(['Directors'], axis = 1)
df_tvshows.fillna({'Directors' : "NA"}, inplace = True)
 
# Cast
df_tvshows.fillna({'Cast' : "NA"}, inplace = True)
 
# Genres
df_tvshows.fillna({'Genres': "NA"}, inplace = True)
 
# Country
df_tvshows.fillna({'Country': "NA"}, inplace = True)
 
# Language
df_tvshows.fillna({'Language': "NA"}, inplace = True)
 
# Plotline
df_tvshows.fillna({'Plotline': "NA"}, inplace = True)
 
# Runtime
# df_tvshows.fillna({'Runtime' : df_tvshows['Runtime'].mean()}, inplace = True)
# df_tvshows['Runtime'] = df_tvshows['Runtime'].astype(int)
df_tvshows.fillna({'Runtime' : "NA"}, inplace = True)
 
# Kind
# df_tvshows.fillna({'Kind': "NA"}, inplace = True)
 
# Type
# df_tvshows.fillna({'Type': "NA"}, inplace = True)
# df_tvshows = df_tvshows.drop(['Type'], axis = 1)
 
# Seasons
# df_tvshows.fillna({'Seasons': 1}, inplace = True)
df_tvshows.fillna({'Seasons': "NA"}, inplace = True)
# df_tvshows = df_tvshows.drop(['Seasons'], axis = 1)
# df_tvshows['Seasons'] = df_tvshows['Seasons'].astype(int)
# df_tvshows.fillna({'Seasons' : df_tvshows['Seasons'].mean()}, inplace = True)
# df_tvshows['Seasons'] = df_tvshows['Seasons'].astype(int)
 
# Service Provider
df_tvshows['Service Provider'] = df_tvshows.loc[:, ['Netflix', 'Prime Video', 'Disney+', 'Hulu']].idxmax(axis = 1)
# df_tvshows.drop(['Netflix','Prime Video','Disney+','Hulu'], axis = 1)

# Removing Duplicate and Missing Entries
df_tvshows.dropna(how = 'any', inplace = True)
df_tvshows.drop_duplicates(inplace = True)


data_investigate(df_tvshows)

No of Rows :  5432
No of Coloums :  21
**************************************************
Colums Names : 
 Index(['ID', 'Title', 'Year', 'Age', 'IMDb', 'Rotten Tomatoes', 'Directors',
       'Cast', 'Genres', 'Country', 'Language', 'Plotline', 'Runtime', 'Kind',
       'Seasons', 'Netflix', 'Hulu', 'Prime Video', 'Disney+', 'Type',
       'Service Provider'],
      dtype='object')
**************************************************
Datatype of Columns : 
 ID                   int64
Title               object
Year                 int64
Age                 object
IMDb                object
Rotten Tomatoes     object
Directors           object
Cast                object
Genres              object
Country             object
Language            object
Plotline            object
Runtime             object
Kind                object
Seasons             object
Netflix              int64
Hulu                 int64
Prime Video          int64
Disney+              int64
Type                 int64
Service Provider    object
dtype: object
**************************************************
Missing Values : 
Series([], dtype: int64)
**************************************************
Missing vaules %age wise :

ID                  0.0
Title               0.0
Year                0.0
Age                 0.0
IMDb                0.0
Rotten Tomatoes     0.0
Directors           0.0
Cast                0.0
Genres              0.0
Country             0.0
Language            0.0
Plotline            0.0
Runtime             0.0
Kind                0.0
Seasons             0.0
Netflix             0.0
Hulu                0.0
Prime Video         0.0
Disney+             0.0
Type                0.0
Service Provider    0.0
dtype: float64
**************************************************
Pictorial Representation :


df_tvshows.head()


df_tvshows.describe()


df_tvshows.corr()


# df_tvshows.sort_values('Year', ascending = True)
# df_tvshows.sort_values('IMDb', ascending = False)


# df_tvshows.to_csv(path_or_buf= '/content/drive/MyDrive/Files/updated_otttvshows.csv', index = False)
 
# path = '/content/drive/MyDrive/Files/'
 
# udf_tvshows = pd.read_csv(path + 'updated_otttvshows.csv')
 
# udf_tvshows


# df_netflix_tvshows = df_tvshows.loc[(df_tvshows['Netflix'] > 0)]
# df_hulu_tvshows = df_tvshows.loc[(df_tvshows['Hulu'] > 0)]
# df_prime_video_tvshows = df_tvshows.loc[(df_tvshows['Prime Video'] > 0)]
# df_disney_tvshows = df_tvshows.loc[(df_tvshows['Disney+'] > 0)]


df_netflix_only_tvshows = df_tvshows[(df_tvshows['Netflix'] == 1) & (df_tvshows['Hulu'] == 0) & (df_tvshows['Prime Video'] == 0 ) & (df_tvshows['Disney+'] == 0)]
df_hulu_only_tvshows = df_tvshows[(df_tvshows['Netflix'] == 0) & (df_tvshows['Hulu'] == 1) & (df_tvshows['Prime Video'] == 0 ) & (df_tvshows['Disney+'] == 0)]
df_prime_video_only_tvshows = df_tvshows[(df_tvshows['Netflix'] == 0) & (df_tvshows['Hulu'] == 0) & (df_tvshows['Prime Video'] == 1 ) & (df_tvshows['Disney+'] == 0)]
df_disney_only_tvshows = df_tvshows[(df_tvshows['Netflix'] == 0) & (df_tvshows['Hulu'] == 0) & (df_tvshows['Prime Video'] == 0 ) & (df_tvshows['Disney+'] == 1)]


df_tvshows_directors = df_tvshows.copy()


df_tvshows_directors.drop(df_tvshows_directors.loc[df_tvshows_directors['Directors'] == "NA"].index, inplace = True)
# df_tvshows_directors = df_tvshows_directors[df_tvshows_directors.Director != "NA"]
# df_tvshows_directors['Director'] = df_tvshows_directors['Director'].astype(str)


df_tvshows_count_directors = df_tvshows_directors.copy()


df_tvshows_director = df_tvshows_directors.copy()


# Create directors dict where key=name and value = number of directors
 
directors = {}
 
for i in df_tvshows_count_directors['Directors'].dropna():
    if i != "NA":
        #print(i,len(i.split(',')))
        directors[i] = len(i.split(','))
    else:
        directors[i] = 0
    
# Add this information to our dataframe as a new column
 
df_tvshows_count_directors['Number of Directors'] = df_tvshows_count_directors['Directors'].map(directors).astype(int)


df_tvshows_mixed_directors = df_tvshows_count_directors.copy()


# Creating distinct dataframes only with the tvshows present on individual streaming platforms
netflix_directors_tvshows = df_tvshows_count_directors.loc[df_tvshows_count_directors['Netflix'] == 1]
hulu_directors_tvshows = df_tvshows_count_directors.loc[df_tvshows_count_directors['Hulu'] == 1]
prime_video_directors_tvshows = df_tvshows_count_directors.loc[df_tvshows_count_directors['Prime Video'] == 1]
disney_directors_tvshows = df_tvshows_count_directors.loc[df_tvshows_count_directors['Disney+'] == 1]


plt.figure(figsize = (10, 10))
corr = df_tvshows_count_directors.corr()
# Plot figsize
fig, ax = plt.subplots(figsize=(10, 8))
# Generate Heat Map, alleast annotations and place floats in map
sns.heatmap(corr, cmap = 'magma', annot = True, fmt = ".2f")
# Apply xticks
plt.xticks(range(len(corr.columns)), corr.columns);
# Apply yticks
plt.yticks(range(len(corr.columns)), corr.columns)
# show plot
plt.show()
fig.show()

<Figure size 720x720 with 0 Axes>


df_directors_most_tvshows = df_tvshows_count_directors.sort_values(by = 'Number of Directors', ascending = False).reset_index()
df_directors_most_tvshows = df_directors_most_tvshows.drop(['index'], axis = 1)
# filter = (df_tvshows_count_directors['Number of Directors'] == (df_tvshows_count_directors['Number of Directors'].max()))
# df_directors_most_tvshows = df_tvshows_count_directors[filter]
 
# mostest_rated_tvshows = df_tvshows_count_directors.loc[df_tvshows_count_directors['Number of Directors'].idxmax()]
 
print('\nTV Shows with Highest Ever Number of Directors are : \n')
df_directors_most_tvshows.head(5)

TV Shows with Highest Ever Number of Directors are :


fig = px.bar(y = df_directors_most_tvshows['Title'][:15],
             x = df_directors_most_tvshows['Number of Directors'][:15], 
             color = df_directors_most_tvshows['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Directors'},
             title  = 'TV Shows with Highest Number of Directors : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


df_directors_least_tvshows = df_tvshows_count_directors.sort_values(by = 'Number of Directors', ascending = True).reset_index()
df_directors_least_tvshows = df_directors_least_tvshows.drop(['index'], axis = 1)
# filter = (df_tvshows_count_directors['Number of Directors'] == (df_tvshows_count_directors['Number of Directors'].min()))
# df_directors_least_tvshows = df_tvshows_count_directors[filter]

print('\nTV Shows with Lowest Ever Number of Directors are : \n')
df_directors_least_tvshows.head(5)

TV Shows with Lowest Ever Number of Directors are :


fig = px.bar(y = df_directors_least_tvshows['Title'][:15],
             x = df_directors_least_tvshows['Number of Directors'][:15], 
             color = df_directors_least_tvshows['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Directors'},
             title  = 'TV Shows with Lowest Number of Directors : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


print(f'''
      Total '{df_tvshows_count_directors['Number of Directors'].unique().shape[0]}' unique Number of Directors s were Given, They were Like this,\n
      
      {df_tvshows_count_directors.sort_values(by = 'Number of Directors', ascending = False)['Number of Directors'].unique()}\n
 
      The Highest Number of Directors Ever Any TV Show Got is '{df_directors_most_tvshows['Title'][0]}' : '{df_directors_most_tvshows['Number of Directors'].max()}'\n
 
      The Lowest Number of Directors Ever Any TV Show Got is '{df_directors_least_tvshows['Title'][0]}' : '{df_directors_least_tvshows['Number of Directors'].min()}'\n
      ''')

      Total '5' unique Number of Directors s were Given, They were Like this,

      
      [5 4 3 2 1]

 
      The Highest Number of Directors Ever Any TV Show Got is 'Stretch Armstrong: The Breakout' : '5'

 
      The Lowest Number of Directors Ever Any TV Show Got is 'A Wednesday!' : '1'


netflix_directors_most_tvshows = df_directors_most_tvshows.loc[df_directors_most_tvshows['Netflix']==1].reset_index()
netflix_directors_most_tvshows = netflix_directors_most_tvshows.drop(['index'], axis = 1)
 
netflix_directors_least_tvshows = df_directors_least_tvshows.loc[df_directors_least_tvshows['Netflix']==1].reset_index()
netflix_directors_least_tvshows = netflix_directors_least_tvshows.drop(['index'], axis = 1)
 
netflix_directors_most_tvshows.head(5)


fig = px.bar(y = netflix_directors_most_tvshows['Title'][:15],
             x = netflix_directors_most_tvshows['Number of Directors'][:15], 
             color = netflix_directors_most_tvshows['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Directors'},
             title  = 'TV Shows with Highest Number of Directors : Netflix')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.bar(y = netflix_directors_least_tvshows['Title'][:15],
             x = netflix_directors_least_tvshows['Number of Directors'][:15], 
             color = netflix_directors_least_tvshows['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Directors'},
             title  = 'TV Shows with Lowest Number of Directors : Netflix')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


hulu_directors_most_tvshows = df_directors_most_tvshows.loc[df_directors_most_tvshows['Hulu']==1].reset_index()
hulu_directors_most_tvshows = hulu_directors_most_tvshows.drop(['index'], axis = 1)
 
hulu_directors_least_tvshows = df_directors_least_tvshows.loc[df_directors_least_tvshows['Hulu']==1].reset_index()
hulu_directors_least_tvshows = hulu_directors_least_tvshows.drop(['index'], axis = 1)
 
hulu_directors_most_tvshows.head(5)


fig = px.bar(y = hulu_directors_most_tvshows['Title'][:15],
             x = hulu_directors_most_tvshows['Number of Directors'][:15], 
             color = hulu_directors_most_tvshows['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Directors'},
             title  = 'TV Shows with Highest Number of Directors : Hulu')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.bar(y = hulu_directors_least_tvshows['Title'][:15],
             x = hulu_directors_least_tvshows['Number of Directors'][:15], 
             color = hulu_directors_least_tvshows['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Directors'},
             title  = 'TV Shows with Lowest Number of Directors : Hulu')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


prime_video_directors_most_tvshows = df_directors_most_tvshows.loc[df_directors_most_tvshows['Prime Video']==1].reset_index()
prime_video_directors_most_tvshows = prime_video_directors_most_tvshows.drop(['index'], axis = 1)
 
prime_video_directors_least_tvshows = df_directors_least_tvshows.loc[df_directors_least_tvshows['Prime Video']==1].reset_index()
prime_video_directors_least_tvshows = prime_video_directors_least_tvshows.drop(['index'], axis = 1)
 
prime_video_directors_most_tvshows.head(5)


fig = px.bar(y = prime_video_directors_most_tvshows['Title'][:15],
             x = prime_video_directors_most_tvshows['Number of Directors'][:15], 
             color = prime_video_directors_most_tvshows['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Directors'},
             title  = 'TV Shows with Highest Number of Directors : Prime Video')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.bar(y = prime_video_directors_least_tvshows['Title'][:15],
             x = prime_video_directors_least_tvshows['Number of Directors'][:15], 
             color = prime_video_directors_least_tvshows['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Directors'},
             title  = 'TV Shows with Lowest Number of Directors : Prime Video')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


disney_directors_most_tvshows = df_directors_most_tvshows.loc[df_directors_most_tvshows['Disney+']==1].reset_index()
disney_directors_most_tvshows = disney_directors_most_tvshows.drop(['index'], axis = 1)
 
disney_directors_least_tvshows = df_directors_least_tvshows.loc[df_directors_least_tvshows['Disney+']==1].reset_index()
disney_directors_least_tvshows = disney_directors_least_tvshows.drop(['index'], axis = 1)
 
disney_directors_most_tvshows.head(5)


fig = px.bar(y = disney_directors_most_tvshows['Title'][:15],
             x = disney_directors_most_tvshows['Number of Directors'][:15], 
             color = disney_directors_most_tvshows['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Directors'},
             title  = 'TV Shows with Highest Number of Directors : Disney+')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


fig = px.bar(y = disney_directors_least_tvshows['Title'][:15],
             x = disney_directors_least_tvshows['Number of Directors'][:15], 
             color = disney_directors_least_tvshows['Number of Directors'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Directors'},
             title  = 'TV Shows with Lowest Number of Directors : Disney+')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


print(f'''
      The TV Show with Highest Number of Directors Ever Got is '{df_directors_most_tvshows['Title'][0]}' : '{df_directors_most_tvshows['Number of Directors'].max()}'\n
      The TV Show with Lowest Number of Directors Ever Got is '{df_directors_least_tvshows['Title'][0]}' : '{df_directors_least_tvshows['Number of Directors'].min()}'\n
      
      The TV Show with Highest Number of Directors on 'Netflix' is '{netflix_directors_most_tvshows['Title'][0]}' : '{netflix_directors_most_tvshows['Number of Directors'].max()}'\n
      The TV Show with Lowest Number of Directors on 'Netflix' is '{netflix_directors_least_tvshows['Title'][0]}' : '{netflix_directors_least_tvshows['Number of Directors'].min()}'\n
      
      The TV Show with Highest Number of Directors on 'Hulu' is '{hulu_directors_most_tvshows['Title'][0]}' : '{hulu_directors_most_tvshows['Number of Directors'].max()}'\n
      The TV Show with Lowest Number of Directors on 'Hulu' is '{hulu_directors_least_tvshows['Title'][0]}' : '{hulu_directors_least_tvshows['Number of Directors'].min()}'\n
      
      The TV Show with Highest Number of Directors on 'Prime Video' is '{prime_video_directors_most_tvshows['Title'][0]}' : '{prime_video_directors_most_tvshows['Number of Directors'].max()}'\n
      The TV Show with Lowest Number of Directors on 'Prime Video' is '{prime_video_directors_least_tvshows['Title'][0]}' : '{prime_video_directors_least_tvshows['Number of Directors'].min()}'\n
      
      The TV Show with Highest Number of Directors on 'Disney+' is '{disney_directors_most_tvshows['Title'][0]}' : '{disney_directors_most_tvshows['Number of Directors'].max()}'\n
      The TV Show with Lowest Number of Directors on 'Disney+' is '{disney_directors_least_tvshows['Title'][0]}' : '{disney_directors_least_tvshows['Number of Directors'].min()}'\n 
      ''')

      The TV Show with Highest Number of Directors Ever Got is 'Stretch Armstrong: The Breakout' : '5'

      The TV Show with Lowest Number of Directors Ever Got is 'A Wednesday!' : '1'

      
      The TV Show with Highest Number of Directors on 'Netflix' is 'Stretch Armstrong: The Breakout' : '5'

      The TV Show with Lowest Number of Directors on 'Netflix' is 'A Wednesday!' : '1'

      
      The TV Show with Highest Number of Directors on 'Hulu' is 'Andy Explores' : '4'

      The TV Show with Lowest Number of Directors on 'Hulu' is 'Food Wars! Shokugeki no Soma' : '1'

      
      The TV Show with Highest Number of Directors on 'Prime Video' is 'Kokkoku, Moment by Moment' : '3'

      The TV Show with Lowest Number of Directors on 'Prime Video' is 'Checkmate' : '1'

      
      The TV Show with Highest Number of Directors on 'Disney+' is 'Ice Age: The Great Egg-Scapade' : '4'

      The TV Show with Lowest Number of Directors on 'Disney+' is 'Invincible' : '1'


print(f'''
      Accross All Platforms the Average Number of Directors is '{round(df_tvshows_count_directors['Number of Directors'].mean(), ndigits = 2)}'\n
      The Average Number of Directors on 'Netflix' is '{round(netflix_directors_tvshows['Number of Directors'].mean(), ndigits = 2)}'\n
      The Average Number of Directors on 'Hulu' is '{round(hulu_directors_tvshows['Number of Directors'].mean(), ndigits = 2)}'\n
      The Average Number of Directors on 'Prime Video' is '{round(prime_video_directors_tvshows['Number of Directors'].mean(), ndigits = 2)}'\n
      The Average Number of Directors on 'Disney+' is '{round(disney_directors_tvshows['Number of Directors'].mean(), ndigits = 2)}'\n 
      ''')

      Accross All Platforms the Average Number of Directors is '1.16'

      The Average Number of Directors on 'Netflix' is '1.3'

      The Average Number of Directors on 'Hulu' is '1.17'

      The Average Number of Directors on 'Prime Video' is '1.1'

      The Average Number of Directors on 'Disney+' is '1.3'


print(f'''
      Accross All Platforms Total Count of Director is '{df_tvshows_count_directors['Number of Directors'].max()}'\n
      Total Count of Director on 'Netflix' is '{netflix_directors_tvshows['Number of Directors'].max()}'\n
      Total Count of Director on 'Hulu' is '{hulu_directors_tvshows['Number of Directors'].max()}'\n
      Total Count of Director on 'Prime Video' is '{prime_video_directors_tvshows['Number of Directors'].max()}'\n
      Total Count of Director on 'Disney+' is '{disney_directors_tvshows['Number of Directors'].max()}'\n 
      ''')

      Accross All Platforms Total Count of Director is '5'

      Total Count of Director on 'Netflix' is '5'

      Total Count of Director on 'Hulu' is '4'

      Total Count of Director on 'Prime Video' is '3'

      Total Count of Director on 'Disney+' is '4'


f, ax = plt.subplots(1, 2 , figsize = (20, 5))
sns.distplot(df_tvshows_count_directors['Number of Directors'],bins = 20, kde = True, ax = ax[0])
sns.boxplot(df_tvshows_count_directors['Number of Directors'], ax = ax[1])
plt.show()


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Number of Directors s Per Platform')
 
# Plotting the information from each dataset into a histogram
sns.histplot(prime_video_directors_tvshows['Number of Directors'], color = 'lightblue', legend = True, kde = True)
sns.histplot(netflix_directors_tvshows['Number of Directors'], color = 'red', legend = True, kde = True)
sns.histplot(hulu_directors_tvshows['Number of Directors'], color = 'lightgreen', legend = True, kde = True)
sns.histplot(disney_directors_tvshows['Number of Directors'], color = 'darkblue', legend = True, kde = True) 
 
# Setting the legend
plt.legend(['Prime Video', 'Netflix', 'Hulu', 'Disney+'])
plt.show()


df_lan = df_tvshows_director['Directors'].str.split(',').apply(pd.Series).stack()
del df_tvshows_director['Directors']
df_lan.index = df_lan.index.droplevel(-1)
df_lan.name = 'Director'
df_tvshows_director = df_tvshows_director.join(df_lan)
df_tvshows_director.drop_duplicates(inplace = True)


df_tvshows_director.head(5)


director_count = df_tvshows_director.groupby('Director')['Title'].count()
director_tvshows = df_tvshows_director.groupby('Director')[['Netflix', 'Hulu', 'Prime Video', 'Disney+']].sum()
director_data_tvshows = pd.concat([director_count, director_tvshows], axis = 1).reset_index().rename(columns = {'Title' : 'TV Shows Count'})
director_data_tvshows = director_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False)


# Director with TV Shows Counts - All Platforms Combined
director_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False)[:10]


fig = px.bar(x = director_data_tvshows['Director'][:50],
             y = director_data_tvshows['TV Shows Count'][:50], 
             color = director_data_tvshows['TV Shows Count'][:50],
             color_continuous_scale = 'Teal_r', 
             labels = { 'x' : 'Director', 'y' : 'TV Shows Count'},
             title  = 'Major Directors : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


df_director_high_tvshows = director_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False).reset_index()
df_director_high_tvshows = df_director_high_tvshows.drop(['index'], axis = 1)
# filter = (director_data_tvshows['TV Shows Count'] == (director_data_tvshows['TV Shows Count'].max()))
# df_director_high_tvshows = director_data_tvshows[filter]
 
# highest_rated_tvshows = director_data_tvshows.loc[director_data_tvshows['TV Shows Count'].idxmax()]
 
print('\nDirector with Highest Ever TV Shows Count are : All Platforms Combined\n')
df_director_high_tvshows.head(5)

Director with Highest Ever TV Shows Count are : All Platforms Combined


fig = px.bar(y = df_director_high_tvshows['Director'][:15],
             x = df_director_high_tvshows['TV Shows Count'][:15], 
             color = df_director_high_tvshows['TV Shows Count'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Director', 'x' : 'TV Shows Count'},
             title  = 'Director with Highest TV Shows : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


df_director_low_tvshows = director_data_tvshows.sort_values(by = 'TV Shows Count', ascending = True).reset_index()
df_director_low_tvshows = df_director_low_tvshows.drop(['index'], axis = 1)
# filter = (director_data_tvshows['TV Shows Count'] == (director_data_tvshows['TV Shows Count'].min()))
# df_director_low_tvshows = director_data_tvshows[filter]

print('\nDirector with Lowest Ever TV Shows Count are : All Platforms Combined\n')
df_director_low_tvshows.head(5)

Director with Lowest Ever TV Shows Count are : All Platforms Combined


fig = px.bar(y = df_director_low_tvshows['Director'][:15],
             x = df_director_low_tvshows['TV Shows Count'][:15], 
             color = df_director_low_tvshows['TV Shows Count'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Director', 'x' : 'TV Shows Count'},
             title  = 'Director with Lowest TV Shows Count : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


print(f'''
      Total '{director_data_tvshows['Director'].unique().shape[0]}' unique Director Count s were Given, They were Like this,\n
      
      {director_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False)['Director'].unique()[:5]}\n
 
      The Highest Ever TV Shows Count Ever Any TV Show Got is '{df_director_high_tvshows['Director'][0]}' : '{df_director_high_tvshows['TV Shows Count'].max()}'\n
 
      The Lowest Ever TV Shows Count Ever Any TV Show Got is '{df_director_low_tvshows['Director'][0]}' : '{df_director_low_tvshows['TV Shows Count'].min()}'\n
      ''')

      Total '307' unique Director Count s were Given, They were Like this,

      
      ['Bob Smeaton' 'Callie T. Wiser' 'Lewis Lovhaug' 'Christopher Menaul'
 'Fabien Beziat']

 
      The Highest Ever TV Shows Count Ever Any TV Show Got is 'Bob Smeaton' : '3'

 
      The Lowest Ever TV Shows Count Ever Any TV Show Got is 'Sol Choi' : '1'


fig = px.pie(director_data_tvshows[:10], names = 'Director', values = 'TV Shows Count', color_discrete_sequence = px.colors.sequential.Teal)
fig.update_traces(textposition = 'inside', textinfo = 'percent+label', title = 'TV Shows Count based on Director')
fig.show()


# netflix_director_tvshows = director_data_tvshows[director_data_tvshows['Netflix'] !=  0].sort_values(by = 'Netflix', ascending = False).reset_index()
# netflix_director_tvshows = netflix_director_tvshows.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)
 
netflix_director_high_tvshows = df_director_high_tvshows.sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_director_high_tvshows = netflix_director_high_tvshows.drop(['index'], axis = 1)
 
netflix_director_low_tvshows = df_director_high_tvshows.sort_values(by = 'Netflix', ascending = True).reset_index()
netflix_director_low_tvshows = netflix_director_low_tvshows.drop(['index'], axis = 1)
 
netflix_director_high_tvshows.head(5)


fig = px.bar(x = netflix_director_high_tvshows['Director'][:15],
             y = netflix_director_high_tvshows['Netflix'][:15], 
             color = netflix_director_high_tvshows['Netflix'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Director', 'x' : 'TV Shows Count'},
             title  = 'Director with Highest TV Shows : Netflix')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


# hulu_director_tvshows = director_data_tvshows[director_data_tvshows['Hulu'] !=  0].sort_values(by = 'Hulu', ascending = False).reset_index()
# hulu_director_tvshows = hulu_director_tvshows.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)
 
hulu_director_high_tvshows = df_director_high_tvshows.sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_director_high_tvshows = hulu_director_high_tvshows.drop(['index'], axis = 1)
 
hulu_director_low_tvshows = df_director_high_tvshows.sort_values(by = 'Hulu', ascending = True).reset_index()
hulu_director_low_tvshows = hulu_director_low_tvshows.drop(['index'], axis = 1)
 
hulu_director_high_tvshows.head(5)


fig = px.bar(x = hulu_director_high_tvshows['Director'][:15],
             y = hulu_director_high_tvshows['Hulu'][:15], 
             color = hulu_director_high_tvshows['Hulu'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Director', 'x' : 'TV Shows Count'},
             title  = 'Director with Highest TV Shows : Hulu')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


# prime_video_director_tvshows = director_data_tvshows[director_data_tvshows['Prime Video'] !=  0].sort_values(by = 'Prime Video', ascending = False).reset_index()
# prime_video_director_tvshows = prime_video_director_tvshows.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'TV Shows Count'], axis = 1)
 
prime_video_director_high_tvshows = df_director_high_tvshows.sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_director_high_tvshows = prime_video_director_high_tvshows.drop(['index'], axis = 1)
 
prime_video_director_low_tvshows = df_director_high_tvshows.sort_values(by = 'Prime Video', ascending = True).reset_index()
prime_video_director_low_tvshows = prime_video_director_low_tvshows.drop(['index'], axis = 1)
 
prime_video_director_high_tvshows.head(5)


fig = px.bar(x = prime_video_director_high_tvshows['Director'][:15],
             y = prime_video_director_high_tvshows['Prime Video'][:15], 
             color = prime_video_director_high_tvshows['Prime Video'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Director', 'x' : 'TV Shows Count'},
             title  = 'Director with Highest TV Shows : Prime Video')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


# disney_director_tvshows = director_data_tvshows[director_data_tvshows['Disney+'] !=  0].sort_values(by = 'Disney+', ascending = False).reset_index()
# disney_director_tvshows = disney_director_tvshows.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'TV Shows Count'], axis = 1)
 
disney_director_high_tvshows = df_director_high_tvshows.sort_values(by = 'Disney+', ascending = False).reset_index()
disney_director_high_tvshows = disney_director_high_tvshows.drop(['index'], axis = 1)
 
disney_director_low_tvshows = df_director_high_tvshows.sort_values(by = 'Disney+', ascending = True).reset_index()
disney_director_low_tvshows = disney_director_low_tvshows.drop(['index'], axis = 1)
 
disney_director_high_tvshows.head(5)


fig = px.bar(x = disney_director_high_tvshows['Director'][:15],
             y = disney_director_high_tvshows['Disney+'][:15], 
             color = disney_director_high_tvshows['Disney+'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'Director', 'x' : 'TV Shows Count'},
             title  = 'Director with Highest TV Shows : Disney+')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


f, ax = plt.subplots(1, 2 , figsize = (20, 5))
sns.distplot(director_data_tvshows['TV Shows Count'], bins = 20, kde = True, ax = ax[0])
sns.boxplot(director_data_tvshows['TV Shows Count'], ax = ax[1])
plt.show()


# Creating distinct dataframes only with the tvshows present on individual streaming platforms
netflix_director_tvshows = director_data_tvshows[director_data_tvshows['Netflix'] !=  0].sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_director_tvshows = netflix_director_tvshows.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)

hulu_director_tvshows = director_data_tvshows[director_data_tvshows['Hulu'] !=  0].sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_director_tvshows = hulu_director_tvshows.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)

prime_video_director_tvshows = director_data_tvshows[director_data_tvshows['Prime Video'] !=  0].sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_director_tvshows = prime_video_director_tvshows.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'TV Shows Count'], axis = 1)

disney_director_tvshows = director_data_tvshows[director_data_tvshows['Disney+'] !=  0].sort_values(by = 'Disney+', ascending = False).reset_index()
disney_director_tvshows = disney_director_tvshows.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'TV Shows Count'], axis = 1)


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Director TV Shows Count Per Platform')
 
# Plotting the information from each dataset into a histogram
 
sns.histplot(disney_director_tvshows['Disney+'][:50], color = 'darkblue', legend = True, kde = True)  
sns.histplot(prime_video_director_tvshows['Prime Video'][:50], color = 'lightblue', legend = True, kde = True)
sns.histplot(netflix_director_tvshows['Netflix'][:50], color = 'red', legend = True, kde = True)
sns.histplot(hulu_director_tvshows['Hulu'][:50], color = 'lightgreen', legend = True, kde = True)                                
 
# Setting the legend
plt.legend(['Disney+', 'Prime Video', 'Netflix', 'Hulu'])
plt.show()


print(f'''
      The Director with Highest TV Shows Count Ever Got is '{df_director_high_tvshows['Director'][0]}' : '{df_director_high_tvshows['TV Shows Count'].max()}'\n
      The Director with Lowest TV Shows Count Ever Got is '{df_director_low_tvshows['Director'][0]}' : '{df_director_low_tvshows['TV Shows Count'].min()}'\n
      
      The Director with Highest TV Shows Count on 'Netflix' is '{netflix_director_high_tvshows['Director'][0]}' : '{netflix_director_high_tvshows['Netflix'].max()}'\n
      The Director with Lowest TV Shows Count on 'Netflix' is '{netflix_director_low_tvshows['Director'][0]}' : '{netflix_director_low_tvshows['Netflix'].min()}'\n
      
      The Director with Highest TV Shows Count on 'Hulu' is '{hulu_director_high_tvshows['Director'][0]}' : '{hulu_director_high_tvshows['Hulu'].max()}'\n
      The Director with Lowest TV Shows Count on 'Hulu' is '{hulu_director_low_tvshows['Director'][0]}' : '{hulu_director_low_tvshows['Hulu'].min()}'\n
      
      The Director with Highest TV Shows Count on 'Prime Video' is '{prime_video_director_high_tvshows['Director'][0]}' : '{prime_video_director_high_tvshows['Prime Video'].max()}'\n
      The Director with Lowest TV Shows Count on 'Prime Video' is '{prime_video_director_low_tvshows['Director'][0]}' : '{prime_video_director_low_tvshows['Prime Video'].min()}'\n
      
      The Director with Highest TV Shows Count on 'Disney+' is '{disney_director_high_tvshows['Director'][0]}' : '{disney_director_high_tvshows['Disney+'].max()}'\n
      The Director with Lowest TV Shows Count on 'Disney+' is '{disney_director_low_tvshows['Director'][0]}' : '{disney_director_low_tvshows['Disney+'].min()}'\n 
      ''')

      The Director with Highest TV Shows Count Ever Got is 'Bob Smeaton' : '3'

      The Director with Lowest TV Shows Count Ever Got is 'Sol Choi' : '1'

      
      The Director with Highest TV Shows Count on 'Netflix' is 'Fabien Beziat' : '2'

      The Director with Lowest TV Shows Count on 'Netflix' is 'Bob Smeaton' : '0'

      
      The Director with Highest TV Shows Count on 'Hulu' is 'Zenith DeGregorio' : '1'

      The Director with Lowest TV Shows Count on 'Hulu' is 'Bob Smeaton' : '0'

      
      The Director with Highest TV Shows Count on 'Prime Video' is 'Bob Smeaton' : '3'

      The Director with Lowest TV Shows Count on 'Prime Video' is 'Julien Leclercq' : '0'

      
      The Director with Highest TV Shows Count on 'Disney+' is 'Robert Stevenson' : '1'

      The Director with Lowest TV Shows Count on 'Disney+' is 'Bob Smeaton' : '0'


# Distribution of tvshows director in each platform
plt.figure(figsize = (20, 5))
plt.title('Director with TV Shows Count for All Platforms')
sns.violinplot(x = director_data_tvshows['TV Shows Count'][:100], color = 'gold', legend = True, kde = True, shade = False)
plt.show()


# Distribution of Director TV Shows Count in each platform
f1, ax1 = plt.subplots(1, 2 , figsize = (20, 5))
sns.violinplot(x = netflix_director_tvshows['Netflix'][:100], color = 'red', ax = ax1[0])
sns.violinplot(x = hulu_director_tvshows['Hulu'][:100], color = 'lightgreen', ax = ax1[1])
 
f2, ax2 = plt.subplots(1, 2 , figsize = (20, 5))
sns.violinplot(x = prime_video_director_tvshows['Prime Video'][:100], color = 'lightblue', ax = ax2[0])
sns.violinplot(x = disney_director_tvshows['Disney+'][:100], color = 'darkblue', ax = ax2[1])
plt.show()


print(f'''
      Accross All Platforms the Average TV Shows Count of Director is '{round(director_data_tvshows['TV Shows Count'].mean(), ndigits = 2)}'\n
      The Average TV Shows Count of Director on 'Netflix' is '{round(netflix_director_tvshows['Netflix'].mean(), ndigits = 2)}'\n
      The Average TV Shows Count of Director on 'Hulu' is '{round(hulu_director_tvshows['Hulu'].mean(), ndigits = 2)}'\n
      The Average TV Shows Count of Director on 'Prime Video' is '{round(prime_video_director_tvshows['Prime Video'].mean(), ndigits = 2)}'\n
      The Average TV Shows Count of Director on 'Disney+' is '{round(disney_director_tvshows['Disney+'].mean(), ndigits = 2)}'\n 
      ''')

      Accross All Platforms the Average TV Shows Count of Director is '1.04'

      The Average TV Shows Count of Director on 'Netflix' is '1.03'

      The Average TV Shows Count of Director on 'Hulu' is '1.0'

      The Average TV Shows Count of Director on 'Prime Video' is '1.03'

      The Average TV Shows Count of Director on 'Disney+' is '1.0'


print(f'''
      Accross All Platforms Total Count of Director is '{director_data_tvshows['Director'].unique().shape[0]}'\n
      Total Count of Director on 'Netflix' is '{netflix_director_tvshows['Director'].unique().shape[0]}'\n
      Total Count of Director on 'Hulu' is '{hulu_director_tvshows['Director'].unique().shape[0]}'\n
      Total Count of Director on 'Prime Video' is '{prime_video_director_tvshows['Director'].unique().shape[0]}'\n
      Total Count of Director on 'Disney+' is '{disney_director_tvshows['Director'].unique().shape[0]}'\n 
      ''')

      Accross All Platforms Total Count of Director is '307'

      Total Count of Director on 'Netflix' is '70'

      Total Count of Director on 'Hulu' is '28'

      Total Count of Director on 'Prime Video' is '196'

      Total Count of Director on 'Disney+' is '26'


plt.figure(figsize = (20, 5))
sns.lineplot(x = director_data_tvshows['Director'][:10], y = director_data_tvshows['Netflix'][:10], color = 'red')
sns.lineplot(x = director_data_tvshows['Director'][:10], y = director_data_tvshows['Hulu'][:10], color = 'lightgreen')
sns.lineplot(x = director_data_tvshows['Director'][:10], y = director_data_tvshows['Prime Video'][:10], color = 'lightblue')
sns.lineplot(x = director_data_tvshows['Director'][:10], y = director_data_tvshows['Disney+'][:10], color = 'darkblue')
plt.xlabel('Director', fontsize = 20)
plt.ylabel('TV Shows Count', fontsize = 20)
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 10))
 
n_d_ax1 = sns.lineplot(y = director_data_tvshows['Director'][:10], x = director_data_tvshows['Netflix'][:10], color = 'red', ax = axes[0, 0])
h_d_ax2 = sns.lineplot(y = director_data_tvshows['Director'][:10], x = director_data_tvshows['Hulu'][:10], color = 'lightgreen', ax = axes[0, 1])
p_d_ax3 = sns.lineplot(y = director_data_tvshows['Director'][:10], x = director_data_tvshows['Prime Video'][:10], color = 'lightblue', ax = axes[1, 0])
d_d_ax4 = sns.lineplot(y = director_data_tvshows['Director'][:10], x = director_data_tvshows['Disney+'][:10], color = 'darkblue', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_d_ax1.title.set_text(labels[0])
h_d_ax2.title.set_text(labels[1])
p_d_ax3.title.set_text(labels[2])
d_d_ax4.title.set_text(labels[3])
 
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_d_ax1 = sns.barplot(y = netflix_director_tvshows['Director'][:10], x = netflix_director_tvshows['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_d_ax2 = sns.barplot(y = hulu_director_tvshows['Director'][:10], x = hulu_director_tvshows['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_d_ax3 = sns.barplot(y = prime_video_director_tvshows['Director'][:10], x = prime_video_director_tvshows['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_d_ax4 = sns.barplot(y = disney_director_tvshows['Director'][:10], x = disney_director_tvshows['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_d_ax1.title.set_text(labels[0])
h_d_ax2.title.set_text(labels[1])
p_d_ax3.title.set_text(labels[2])
d_d_ax4.title.set_text(labels[3])
 
plt.show()


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Director  TV Shows Count Per Platform')
 
# Plotting the information from each dataset into a histogram
sns.kdeplot(netflix_director_tvshows['Netflix'][:10], color = 'red', legend = True)
sns.kdeplot(hulu_director_tvshows['Hulu'][:10], color = 'green', legend = True)
sns.kdeplot(prime_video_director_tvshows['Prime Video'][:10], color = 'lightblue', legend = True)
sns.kdeplot(disney_director_tvshows['Disney+'][:10], color = 'darkblue', legend = True)                                      
                                      
# Setting the legend
plt.legend(['Netflix', 'Hulu', 'Prime Video', 'Disney+'])
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_d_ax1 = sns.barplot(y = director_data_tvshows['Director'][:10], x = director_data_tvshows['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_d_ax2 = sns.barplot(y = director_data_tvshows['Director'][:10], x = director_data_tvshows['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_d_ax3 = sns.barplot(y = director_data_tvshows['Director'][:10], x = director_data_tvshows['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_d_ax4 = sns.barplot(y = director_data_tvshows['Director'][:10], x = director_data_tvshows['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_d_ax1.title.set_text(labels[0])
h_d_ax2.title.set_text(labels[1])
p_d_ax3.title.set_text(labels[2])
d_d_ax4.title.set_text(labels[3])
 
plt.show()


df_tvshows_mixed_directors.drop(df_tvshows_mixed_directors.loc[df_tvshows_mixed_directors['Directors'] == "NA"].index, inplace = True)
# df_tvshows_mixed_directors = df_tvshows_mixed_directors[df_tvshows_mixed_directors.Director != "NA"]
df_tvshows_mixed_directors.drop(df_tvshows_mixed_directors.loc[df_tvshows_mixed_directors['Number of Directors'] == 1].index, inplace = True)


df_tvshows_mixed_directors.head(5)


mixed_directors_count = df_tvshows_mixed_directors.groupby('Directors')['Title'].count()
mixed_directors_tvshows = df_tvshows_mixed_directors.groupby('Directors')[['Netflix', 'Hulu', 'Prime Video', 'Disney+']].sum()
mixed_directors_data_tvshows = pd.concat([mixed_directors_count, mixed_directors_tvshows], axis = 1).reset_index().rename(columns = {'Title' : 'TV Shows Count', 'Directors' : 'Mixed Director'})
mixed_directors_data_tvshows = mixed_directors_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False)


mixed_directors_data_tvshows.head(5)


# Mixed Director with TV Shows Counts - All Platforms Combined
mixed_directors_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False)[:10]


df_mixed_directors_high_tvshows = mixed_directors_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False).reset_index()
df_mixed_directors_high_tvshows = df_mixed_directors_high_tvshows.drop(['index'], axis = 1)
# filter = (mixed_directors_data_tvshows['TV Shows Count'] = =  (mixed_directors_data_tvshows['TV Shows Count'].max()))
# df_mixed_directors_high_tvshows = mixed_directors_data_tvshows[filter]
 
# highest_rated_tvshows = mixed_directors_data_tvshows.loc[mixed_directors_data_tvshows['TV Shows Count'].idxmax()]
 
print('\nMixed Director with Highest Ever TV Shows Count are : All Platforms Combined\n')
df_mixed_directors_high_tvshows.head(5)

Mixed Director with Highest Ever TV Shows Count are : All Platforms Combined


fig = px.bar(y = df_mixed_directors_high_tvshows['Mixed Director'][:15],
             x = df_mixed_directors_high_tvshows['TV Shows Count'][:15], 
             color = df_mixed_directors_high_tvshows['TV Shows Count'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Mixed Director'},
             title  = 'TV Shows with Highest Number of Mixed Directors : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


df_mixed_directors_low_tvshows = mixed_directors_data_tvshows.sort_values(by = 'TV Shows Count', ascending = True).reset_index()
df_mixed_directors_low_tvshows = df_mixed_directors_low_tvshows.drop(['index'], axis = 1)
# filter = (mixed_directors_data_tvshows['TV Shows Count'] = =  (mixed_directors_data_tvshows['TV Shows Count'].min()))
# df_mixed_directors_low_tvshows = mixed_directors_data_tvshows[filter]
 
print('\nMixed Director with Lowest Ever TV Shows Count are : All Platforms Combined\n')
df_mixed_directors_low_tvshows.head(5)

Mixed Director with Lowest Ever TV Shows Count are : All Platforms Combined


fig = px.bar(y = df_mixed_directors_low_tvshows['Mixed Director'][:15],
             x = df_mixed_directors_low_tvshows['TV Shows Count'][:15], 
             color = df_mixed_directors_low_tvshows['TV Shows Count'][:15],
             color_continuous_scale = 'Teal_r', 
             labels = { 'y' : 'TV Shows', 'x' : 'Number of Mixed Director'},
             title  = 'TV Shows with Lowest Number of Mixed Directors : All Platforms')

fig.update_layout(plot_bgcolor = 'white')
fig.show()


print(f'''
      Total '{df_tvshows_directors['Directors'].count()}' Titles are available on All Platforms, out of which\n
      You Can Choose to see TV Shows from Total '{mixed_directors_data_tvshows['Mixed Director'].unique().shape[0]}' Mixed Director, They were Like this, \n
 
      {mixed_directors_data_tvshows.sort_values(by = 'TV Shows Count', ascending = False)['Mixed Director'].head(5).unique()} etc. \n
 
      The Mixed Director with Highest TV Shows Count have '{mixed_directors_data_tvshows['TV Shows Count'].max()}' TV Shows Available is '{df_mixed_directors_high_tvshows['Mixed Director'][0]}', &\n
      The Mixed Director with Lowest TV Shows Count have '{mixed_directors_data_tvshows['TV Shows Count'].min()}' TV Shows Available is '{df_mixed_directors_low_tvshows['Mixed Director'][0]}'
      ''')

      Total '274' Titles are available on All Platforms, out of which

      You Can Choose to see TV Shows from Total '31' Mixed Director, They were Like this, 

 
      ['Fabien Beziat,Hugues Nancy' 'Nikolay Kozlov,Aleksandr Lyutkevich'
 'Bruno Mattei,Claudio Fragasso' 'Daniel Zuckerbrot,Donna Zuckerbrot'
 'David Belton,Andy Byatt'] etc. 

 
      The Mixed Director with Highest TV Shows Count have '2' TV Shows Available is 'Fabien Beziat,Hugues Nancy', &

      The Mixed Director with Lowest TV Shows Count have '1' TV Shows Available is 'Rajesh Ranshinge,Prabal Baruah,Suleman Quadri,Udayan Pradeep Shukla'


fig = px.pie(mixed_directors_data_tvshows[:4], names = 'Mixed Director', values = 'TV Shows Count', color_discrete_sequence = px.colors.sequential.Teal)
fig.update_traces(textposition = 'inside', textinfo = 'percent+label', title = 'TV Shows Count based on Mixed Director')
fig.show()


# netflix_mixed_directors_tvshows = mixed_directors_data_tvshows[mixed_directors_data_tvshows['Netflix'] !=  0].sort_values(by = 'Netflix', ascending = False).reset_index()
# netflix_mixed_directors_tvshows = netflix_mixed_directors_tvshows.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)
 
netflix_mixed_directors_high_tvshows = df_mixed_directors_high_tvshows.sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_mixed_directors_high_tvshows = netflix_mixed_directors_high_tvshows.drop(['index'], axis = 1)
 
netflix_mixed_directors_low_tvshows = df_mixed_directors_high_tvshows.sort_values(by = 'Netflix', ascending = True).reset_index()
netflix_mixed_directors_low_tvshows = netflix_mixed_directors_low_tvshows.drop(['index'], axis = 1)
 
netflix_mixed_directors_high_tvshows.head(5)


# hulu_mixed_directors_tvshows = mixed_directors_data_tvshows[mixed_directors_data_tvshows['Hulu'] !=  0].sort_values(by = 'Hulu', ascending = False).reset_index()
# hulu_mixed_directors_tvshows = hulu_mixed_directors_tvshows.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)
 
hulu_mixed_directors_high_tvshows = df_mixed_directors_high_tvshows.sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_mixed_directors_high_tvshows = hulu_mixed_directors_high_tvshows.drop(['index'], axis = 1)
 
hulu_mixed_directors_low_tvshows = df_mixed_directors_high_tvshows.sort_values(by = 'Hulu', ascending = True).reset_index()
hulu_mixed_directors_low_tvshows = hulu_mixed_directors_low_tvshows.drop(['index'], axis = 1)
 
hulu_mixed_directors_high_tvshows.head(5)


# prime_video_mixed_directors_tvshows = mixed_directors_data_tvshows[mixed_directors_data_tvshows['Prime Video'] !=  0].sort_values(by = 'Prime Video', ascending = False).reset_index()
# prime_video_mixed_directors_tvshows = prime_video_mixed_directors_tvshows.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'TV Shows Count'], axis = 1)
 
prime_video_mixed_directors_high_tvshows = df_mixed_directors_high_tvshows.sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_mixed_directors_high_tvshows = prime_video_mixed_directors_high_tvshows.drop(['index'], axis = 1)
 
prime_video_mixed_directors_low_tvshows = df_mixed_directors_high_tvshows.sort_values(by = 'Prime Video', ascending = True).reset_index()
prime_video_mixed_directors_low_tvshows = prime_video_mixed_directors_low_tvshows.drop(['index'], axis = 1)
 
prime_video_mixed_directors_high_tvshows.head(5)


# disney_mixed_directors_tvshows = mixed_directors_data_tvshows[mixed_directors_data_tvshows['Disney+'] !=  0].sort_values(by = 'Disney+', ascending = False).reset_index()
# disney_mixed_directors_tvshows = disney_mixed_directors_tvshows.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'TV Shows Count'], axis = 1)
 
disney_mixed_directors_high_tvshows = df_mixed_directors_high_tvshows.sort_values(by = 'Disney+', ascending = False).reset_index()
disney_mixed_directors_high_tvshows = disney_mixed_directors_high_tvshows.drop(['index'], axis = 1)
 
disney_mixed_directors_low_tvshows = df_mixed_directors_high_tvshows.sort_values(by = 'Disney+', ascending = True).reset_index()
disney_mixed_directors_low_tvshows = disney_mixed_directors_low_tvshows.drop(['index'], axis = 1)
 
disney_mixed_directors_high_tvshows.head(5)


f, ax = plt.subplots(1, 2 , figsize = (20, 5))
sns.distplot(mixed_directors_data_tvshows['TV Shows Count'], bins = 20, kde = True, ax = ax[0])
sns.boxplot(mixed_directors_data_tvshows['TV Shows Count'], ax = ax[1])
plt.show()


# Creating distinct dataframes only with the tvshows present on individual streaming platforms
netflix_mixed_directors_tvshows = mixed_directors_data_tvshows[mixed_directors_data_tvshows['Netflix'] !=  0].sort_values(by = 'Netflix', ascending = False).reset_index()
netflix_mixed_directors_tvshows = netflix_mixed_directors_tvshows.drop(['index', 'Hulu', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)

hulu_mixed_directors_tvshows = mixed_directors_data_tvshows[mixed_directors_data_tvshows['Hulu'] !=  0].sort_values(by = 'Hulu', ascending = False).reset_index()
hulu_mixed_directors_tvshows = hulu_mixed_directors_tvshows.drop(['index', 'Netflix', 'Prime Video', 'Disney+', 'TV Shows Count'], axis = 1)

prime_video_mixed_directors_tvshows = mixed_directors_data_tvshows[mixed_directors_data_tvshows['Prime Video'] !=  0].sort_values(by = 'Prime Video', ascending = False).reset_index()
prime_video_mixed_directors_tvshows = prime_video_mixed_directors_tvshows.drop(['index', 'Netflix', 'Hulu', 'Disney+', 'TV Shows Count'], axis = 1)

disney_mixed_directors_tvshows = mixed_directors_data_tvshows[mixed_directors_data_tvshows['Disney+'] !=  0].sort_values(by = 'Disney+', ascending = False).reset_index()
disney_mixed_directors_tvshows = disney_mixed_directors_tvshows.drop(['index', 'Netflix', 'Hulu', 'Prime Video', 'TV Shows Count'], axis = 1)


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Mixed Director TV Shows Count Per Platform')
 
# Plotting the information from each dataset into a histogram
 
sns.histplot(prime_video_mixed_directors_tvshows['Prime Video'][:100], color = 'lightblue', legend = True, kde = True)
sns.histplot(netflix_mixed_directors_tvshows['Netflix'][:100], color = 'red', legend = True, kde = True)
sns.histplot(hulu_mixed_directors_tvshows['Hulu'][:100], color = 'lightgreen', legend = True, kde = True)
sns.histplot(disney_mixed_directors_tvshows['Disney+'][:100], color = 'darkblue', legend = True, kde = True)                                
 
# Setting the legend
plt.legend(['Prime Video', 'Netflix', 'Hulu', 'Disney+'])
plt.show()


print(f'''
      The Mixed Director with Highest TV Shows Count Ever Got is '{df_mixed_directors_high_tvshows['Mixed Director'][0]}' : '{df_mixed_directors_high_tvshows['TV Shows Count'].max()}'\n
      The Mixed Director with Lowest TV Shows Count Ever Got is '{df_mixed_directors_low_tvshows['Mixed Director'][0]}' : '{df_mixed_directors_low_tvshows['TV Shows Count'].min()}'\n
      
      The Mixed Director with Highest TV Shows Count on 'Netflix' is '{netflix_mixed_directors_high_tvshows['Mixed Director'][0]}' : '{netflix_mixed_directors_high_tvshows['Netflix'].max()}'\n
      The Mixed Director with Lowest TV Shows Count on 'Netflix' is '{netflix_mixed_directors_low_tvshows['Mixed Director'][0]}' : '{netflix_mixed_directors_low_tvshows['Netflix'].min()}'\n
      
      The Mixed Director with Highest TV Shows Count on 'Hulu' is '{hulu_mixed_directors_high_tvshows['Mixed Director'][0]}' : '{hulu_mixed_directors_high_tvshows['Hulu'].max()}'\n
      The Mixed Director with Lowest TV Shows Count on 'Hulu' is '{hulu_mixed_directors_low_tvshows['Mixed Director'][0]}' : '{hulu_mixed_directors_low_tvshows['Hulu'].min()}'\n
      
      The Mixed Director with Highest TV Shows Count on 'Prime Video' is '{prime_video_mixed_directors_high_tvshows['Mixed Director'][0]}' : '{prime_video_mixed_directors_high_tvshows['Prime Video'].max()}'\n
      The Mixed Director with Lowest TV Shows Count on 'Prime Video' is '{prime_video_mixed_directors_low_tvshows['Mixed Director'][0]}' : '{prime_video_mixed_directors_low_tvshows['Prime Video'].min()}'\n
      
      The Mixed Director with Highest TV Shows Count on 'Disney+' is '{disney_mixed_directors_high_tvshows['Mixed Director'][0]}' : '{disney_mixed_directors_high_tvshows['Disney+'].max()}'\n
      The Mixed Director with Lowest TV Shows Count on 'Disney+' is '{disney_mixed_directors_low_tvshows['Mixed Director'][0]}' : '{disney_mixed_directors_low_tvshows['Disney+'].min()}'\n 
      ''')

      The Mixed Director with Highest TV Shows Count Ever Got is 'Fabien Beziat,Hugues Nancy' : '2'

      The Mixed Director with Lowest TV Shows Count Ever Got is 'Rajesh Ranshinge,Prabal Baruah,Suleman Quadri,Udayan Pradeep Shukla' : '1'

      
      The Mixed Director with Highest TV Shows Count on 'Netflix' is 'Fabien Beziat,Hugues Nancy' : '2'

      The Mixed Director with Lowest TV Shows Count on 'Netflix' is 'William Beaudine,Wilfred Jackson' : '0'

      
      The Mixed Director with Highest TV Shows Count on 'Hulu' is 'Aaron Basch,Trevor Morris,Chris Olivas,Peter Schmid-Schoenbein' : '1'

      The Mixed Director with Lowest TV Shows Count on 'Hulu' is 'Fabien Beziat,Hugues Nancy' : '0'

      
      The Mixed Director with Highest TV Shows Count on 'Prime Video' is 'Kanye West,Alexandre Moors,Elon Rutberg' : '1'

      The Mixed Director with Lowest TV Shows Count on 'Prime Video' is 'Fabien Beziat,Hugues Nancy' : '0'

      
      The Mixed Director with Highest TV Shows Count on 'Disney+' is 'William Beaudine,Wilfred Jackson' : '1'

      The Mixed Director with Lowest TV Shows Count on 'Disney+' is 'Fabien Beziat,Hugues Nancy' : '0'


print(f'''
      Accross All Platforms the Average TV Shows Count of Mixed Director is '{round(mixed_directors_data_tvshows['TV Shows Count'].mean(), ndigits = 2)}'\n
      The Average TV Shows Count of Mixed Director on 'Netflix' is '{round(netflix_mixed_directors_tvshows['Netflix'].mean(), ndigits = 2)}'\n
      The Average TV Shows Count of Mixed Director on 'Hulu' is '{round(hulu_mixed_directors_tvshows['Hulu'].mean(), ndigits = 2)}'\n
      The Average TV Shows Count of Mixed Director on 'Prime Video' is '{round(prime_video_mixed_directors_tvshows['Prime Video'].mean(), ndigits = 2)}'\n
      The Average TV Shows Count of Mixed Director on 'Disney+' is '{round(disney_mixed_directors_tvshows['Disney+'].mean(), ndigits = 2)}'\n 
      ''')

      Accross All Platforms the Average TV Shows Count of Mixed Director is '1.03'

      The Average TV Shows Count of Mixed Director on 'Netflix' is '1.11'

      The Average TV Shows Count of Mixed Director on 'Hulu' is '1.0'

      The Average TV Shows Count of Mixed Director on 'Prime Video' is '1.0'

      The Average TV Shows Count of Mixed Director on 'Disney+' is '1.0'


print(f'''
      Accross All Platforms Total Count of Mixed Director is '{mixed_directors_data_tvshows['Mixed Director'].unique().shape[0]}'\n
      Total Count of Mixed Director on 'Netflix' is '{netflix_mixed_directors_tvshows['Mixed Director'].unique().shape[0]}'\n
      Total Count of Mixed Director on 'Hulu' is '{hulu_mixed_directors_tvshows['Mixed Director'].unique().shape[0]}'\n
      Total Count of Mixed Director on 'Prime Video' is '{prime_video_mixed_directors_tvshows['Mixed Director'].unique().shape[0]}'\n
      Total Count of Mixed Director on 'Disney+' is '{disney_mixed_directors_tvshows['Mixed Director'].unique().shape[0]}'\n 
      ''')

      Accross All Platforms Total Count of Mixed Director is '31'

      Total Count of Mixed Director on 'Netflix' is '9'

      Total Count of Mixed Director on 'Hulu' is '2'

      Total Count of Mixed Director on 'Prime Video' is '16'

      Total Count of Mixed Director on 'Disney+' is '4'


plt.figure(figsize = (20, 5))
sns.lineplot(x = mixed_directors_data_tvshows['Mixed Director'][:5], y = mixed_directors_data_tvshows['Netflix'][:5], color = 'red')
sns.lineplot(x = mixed_directors_data_tvshows['Mixed Director'][:5], y = mixed_directors_data_tvshows['Hulu'][:5], color = 'lightgreen')
sns.lineplot(x = mixed_directors_data_tvshows['Mixed Director'][:5], y = mixed_directors_data_tvshows['Prime Video'][:5], color = 'lightblue')
sns.lineplot(x = mixed_directors_data_tvshows['Mixed Director'][:5], y = mixed_directors_data_tvshows['Disney+'][:5], color = 'darkblue')
plt.xlabel('Mixed Director', fontsize = 15)
plt.ylabel('TV Shows Count', fontsize = 15)
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_d_ax1 = sns.barplot(x = mixed_directors_data_tvshows['Mixed Director'][:10], y = mixed_directors_data_tvshows['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_d_ax2 = sns.barplot(x = mixed_directors_data_tvshows['Mixed Director'][:10], y = mixed_directors_data_tvshows['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_d_ax3 = sns.barplot(x = mixed_directors_data_tvshows['Mixed Director'][:10], y = mixed_directors_data_tvshows['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_d_ax4 = sns.barplot(x = mixed_directors_data_tvshows['Mixed Director'][:10], y = mixed_directors_data_tvshows['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_d_ax1.title.set_text(labels[0])
h_d_ax2.title.set_text(labels[1])
p_d_ax3.title.set_text(labels[2])
d_d_ax4.title.set_text(labels[3])
 
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 10))
 
n_md_ax1 = sns.lineplot(x = mixed_directors_data_tvshows['Mixed Director'][:10], y = mixed_directors_data_tvshows['Netflix'][:10], color = 'red', ax = axes[0, 0])
h_md_ax2 = sns.lineplot(x = mixed_directors_data_tvshows['Mixed Director'][:10], y = mixed_directors_data_tvshows['Hulu'][:10], color = 'lightgreen', ax = axes[0, 1])
p_md_ax3 = sns.lineplot(x = mixed_directors_data_tvshows['Mixed Director'][:10], y = mixed_directors_data_tvshows['Prime Video'][:10], color = 'lightblue', ax = axes[1, 0])
d_md_ax4 = sns.lineplot(x = mixed_directors_data_tvshows['Mixed Director'][:10], y = mixed_directors_data_tvshows['Disney+'][:10], color = 'darkblue', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_md_ax1.title.set_text(labels[0])
h_md_ax2.title.set_text(labels[1])
p_md_ax3.title.set_text(labels[2])
d_md_ax4.title.set_text(labels[3])
 
plt.show()


# Defining plot size and title
plt.figure(figsize = (20, 5))
plt.title('Mixed Director  TV Shows Count Per Platform')
 
# Plotting the information from each dataset into a histogram
sns.kdeplot(netflix_mixed_directors_tvshows['Netflix'][:50], color = 'red', legend = True)
sns.kdeplot(hulu_mixed_directors_tvshows['Hulu'][:50], color = 'green', legend = True)
sns.kdeplot(prime_video_mixed_directors_tvshows['Prime Video'][:50], color = 'lightblue', legend = True)
sns.kdeplot(disney_mixed_directors_tvshows['Disney+'][:50], color = 'darkblue', legend = True)                                      

# Setting the legend
plt.legend(['Netflix', 'Hulu', 'Prime Video', 'Disney+'])
plt.show()


fig, axes = plt.subplots(2, 2, figsize = (20 , 20))
 
n_md_ax1 = sns.barplot(x = netflix_mixed_directors_tvshows['Mixed Director'][:10], y = netflix_mixed_directors_tvshows['Netflix'][:10], palette = 'Reds_r', ax = axes[0, 0])
h_md_ax2 = sns.barplot(x = hulu_mixed_directors_tvshows['Mixed Director'][:10], y = hulu_mixed_directors_tvshows['Hulu'][:10], palette = 'Greens_r', ax = axes[0, 1])
p_md_ax3 = sns.barplot(x = prime_video_mixed_directors_tvshows['Mixed Director'][:10], y = prime_video_mixed_directors_tvshows['Prime Video'][:10], palette = 'Blues_r', ax = axes[1, 0])
d_md_ax4 = sns.barplot(x = disney_mixed_directors_tvshows['Mixed Director'][:10], y = disney_mixed_directors_tvshows['Disney+'][:10], palette = 'BuPu_r', ax = axes[1, 1])
 
labels = ['Netflix', 'Hulu', 'Prime Video', 'Disney+']
 
n_md_ax1.title.set_text(labels[0])
h_md_ax2.title.set_text(labels[1])
p_md_ax3.title.set_text(labels[2])
d_md_ax4.title.set_text(labels[3])
 
plt.show()


fig = go.Figure(go.Funnel(y = mixed_directors_data_tvshows['Mixed Director'][:10], x = mixed_directors_data_tvshows['TV Shows Count'][:10]))
fig.show()

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	Language	Plotline	Runtime	Kind	Seasons	Netflix	Prime Video	Disney+	Type
0	1	Snowpiercer	2013	18+	6.9	94%	NaN	Daveed Diggs,Iddo Goldberg,Mickey Sumner,Aliso...	Action,Drama,Sci-Fi,Thriller	United States	English	Set seven years after the world has become a f...	60.0	tv series	3.0	1	0	0	1
1	2	Philadelphia	1993	13+	8.8	80%	NaN	Charlie Day,Glenn Howerton,Rob McElhenney,Kait...	Comedy	United States	English	The gang, 5 raging alcoholic, narcissists run ...	22.0	tv series	18.0	1	0	0	1
2	3	Roma	2018	18+	8.7	93%	NaN	Kevin McKidd,Ray Stevenson,Polly Walker,Kerry ...	Action,Drama,History,Romance,War	United Kingdom,United States	English	In this British historical drama, the turbulen...	52.0	tv series	2.0	1	0	0	1
3	4	Amy	2015	18+	7.0	87%	NaN	Amy Brenneman,Richard T. Jones,Jessica Tuck,Ma...	Drama	United States	English	A family drama focused on three generations of...	60.0	tv series	6.0	1	1	1	1
4	5	The Young Offenders	2016	NaN	8.0	100%	NaN	Alex Murphy,Chris Walley,Hilary Rose,Dominic M...	Comedy	United Kingdom,Ireland	English	NaN	30.0	tv series	3.0	1	0	0	1

	ID	Year	Netflix	Hulu	Prime Video	Disney+	Type
count	5432.000000	5432.000000	5432.000000	5432.000000	5432.000000	5432.000000	5432.0
mean	2716.500000	2010.668446	0.341311	0.293999	0.403351	0.033689	1.0
std	1568.227662	11.726176	0.474193	0.455633	0.490615	0.180445	0.0
min	1.000000	1901.000000	0.000000	0.000000	0.000000	0.000000	1.0
25%	1358.750000	2009.000000	0.000000	0.000000	0.000000	0.000000	1.0
50%	2716.500000	2014.000000	0.000000	0.000000	0.000000	0.000000	1.0
75%	4074.250000	2017.000000	1.000000	1.000000	1.000000	0.000000	1.0
max	5432.000000	2020.000000	1.000000	1.000000	1.000000	1.000000	1.0

	ID	Year	Netflix	Hulu	Prime Video	Disney+	Type
ID	1.000000	-0.031346	-0.646330	0.034293	0.441264	0.195409	NaN
Year	-0.031346	1.000000	0.222316	-0.065807	-0.198675	-0.022741	NaN
Netflix	-0.646330	0.222316	1.000000	-0.366515	-0.515086	-0.119344	NaN
Hulu	0.034293	-0.065807	-0.366515	1.000000	-0.377374	-0.075701	NaN
Prime Video	0.441264	-0.198675	-0.515086	-0.377374	1.000000	-0.151442	NaN
Disney+	0.195409	-0.022741	-0.119344	-0.075701	-0.151442	1.000000	NaN
Type	NaN	NaN	NaN	NaN	NaN	NaN	NaN

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	...	Runtime	Kind	Seasons	Netflix	Hulu	Disney+	Type	Service Provider	Number of Directors
0	54	Stretch Armstrong: The Breakout	2018	NR	6.6	NA	Victor Cook,Kevin Altieri,Alan Caldwell,Victor...	Ogie Banks,Clancy Brown,Yvette Nicole Brown,Ga...	Animation,Short,Action,Adventure,Comedy,Sci-Fi	NA	...	NA	tv series	NA	1	0	0	1	Netflix	5
1	3618	Andy Explores	2019	NR	NA	NA	Aaron Basch,Trevor Morris,Chris Olivas,Peter S...	Ronnie Das,Jordan Sanchez,James Stone,Theresa ...	Documentary,Family,News,Reality-TV	NA	...	NA	tv series	NA	0	1	0	1	Hulu	4
2	1560	Trailer Park Boys: Out of the Park: Europe	2016	18	7.8	NA	Gary Howsam,Mike Smith,John Paul Tremblay,Robb...	John Paul Tremblay,Robb Wells,Mike Smith,Tom M...	Adventure,Comedy,Crime,Drama	NA	...	NA	tv series	NA	1	0	0	1	Netflix	4
3	26	K. D.	2019	NR	8.6	87	Rajesh Ranshinge,Prabal Baruah,Suleman Quadri,...	Maya Alagh,Nayan Bhatt,Manav Gohil,Darshan Jar...	Crime,Drama,Mystery,Thriller	NA	...	45	tv series	NA	1	0	0	1	Netflix	4
4	492	Ice Age: The Great Egg-Scapade	2016	7	5.9	NA	Paul Stodolny,Ricardo Curtis,Steve Martino,Mik...	Blake Anderson,Tyree Brown,David Cowgill,Jenni...	Animation,Short,Adventure,Comedy,Family	United States	...	25	tv series	NA	0	0	1	1	Disney+	4

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	...	Runtime	Kind	Seasons	Netflix	Prime Video	Type	Service Provider	Number of Directors
0	7	A Wednesday!	2008	NR	8.1	NA	Neeraj Pandey	NA	Comedy,Family,Fantasy,Horror	United States	...	104	tv series	1	1	0	1	Netflix	1
1	411	Checkmate	2015	NR	7.6	NA	Timothy Woodward Jr.	Anthony George,Doug McClure,Sebastian Cabot,Ke...	Crime,Drama,Mystery	United States	...	60	tv series	2	0	1	1	Prime Video	1
2	413	Demented Death Farm Massacre	1971	18	8.3	NA	Brad Jones	Brad Jones	Comedy	NA	...	11	tv series	NA	0	1	1	Prime Video	1
3	424	Renfield the Undead	2011	NR	2.8	NA	Bob Willems	Cory Hart,Julin,Denise Williamson,Natalie Popo...	Comedy,Drama,Horror,Mystery,Sci-Fi,Thriller	NA	...	111	tv series	NA	0	1	1	Prime Video	1
4	427	Universal Soldiers	2007	NR	6.1	56	Tetsurô Amino	Yasunori Matsumoto,Akira Kamiya,Hirotaka Suzuo...	Animation,Action,Drama,Sci-Fi	Japan	...	150	tv series	1	0	1	1	Prime Video	1

	ID	Title	Year	Age	IMDb	Rotten Tomatoes	Directors	Cast	Genres	Country	...	Runtime	Kind	Seasons	Prime Video	Type	Service Provider	Number of Directors
0	4231	Kokkoku, Moment by Moment	2018	18	8.1	NA	Takahiro Kawakoshi,Yoji Minaharu,Yoshimitsu Ôh...	Amber Lee Connors,Marissa Lenti,Carl Masterson...	Animation,Drama,Mystery,Thriller	NA	...	24	tv series	NA	1	1	Prime Video	3
1	247	Cruel Summer	2016	NR	8.2	NA	Kanye West,Alexandre Moors,Elon Rutberg	Chiara Aurelia,Andrea Anders,Benjamin J. Cain ...	Drama,Mystery,Thriller	United States	...	45	tv series	1	1	1	Prime Video	3
2	402	Guns And Guts	1974	NR	5.2	NA	Sam Dolan,Tim Evans	NA	Documentary	NA	...	48	tv series	NA	1	1	Prime Video	2
3	165	Zog	2019	NR	7.4	NA	Max Lang,Daniel Snaddon	Lenny Henry,Tracey Ullman,Patsy Ferran,Rocco W...	Animation,Short,Comedy,Family	United Kingdom	...	26	tv series	NA	1	1	Prime Video	2
4	150	The Day of the Triffids	1962	NR	5.6	76	Steve Sekely,Freddie Francis	Dougray Scott,Joely Richardson,Eddie Izzard,Br...	Action,Horror,Sci-Fi,Thriller	United Kingdom,Canada	...	186	tv series	1	1	1	Prime Video	2

	Director	TV Shows Count	Netflix	Prime Video	Disney+
37	Bob Smeaton	3	0	3	0
47	Callie T. Wiser	2	0	2	0
169	Lewis Lovhaug	2	0	1	1
58	Christopher Menaul	2	1	1	0
88	Fabien Beziat	2	2	0	0
232	Rick Morales	2	1	1	0
224	Randall MacLowry	2	0	2	0
132	Jeremy Marre	2	0	2	0
113	Hugues Nancy	2	2	0	0
181	Matthew Longfellow	2	0	2	0

	Director	TV Shows Count	Netflix	Prime Video	Disney+
0	Sol Choi	1	0	0	1
1	Adolfo Alix Jr.	1	0	1	0
2	Alan Caldwell	1	1	0	0
3	Alan Lewens	1	0	1	0
4	Alastair Layzell	1	0	1	0

	Director	TV Shows Count	Netflix
0	Fabien Beziat	2	2
1	Hugues Nancy	2	2
2	Julien Leclercq	1	1
3	Federico Veiroj	1	1
4	Nagesh Kukunoor	1	1

	Director	TV Shows Count	Hulu	Prime Video
0	Zenith DeGregorio	1	1	0
1	Brian K. Roberts	1	1	0
2	Grey Lockwood	1	1	0
3	Charles S. Dubin	1	1	0
4	Shane Dawson	1	1	1

	Director	TV Shows Count	Disney+
0	Robert Stevenson	1	1
1	Wilfred Jackson	1	1
2	Steve Martino	1	1
3	Sotiris Tsafoulias	1	1
4	Sue Perrotto	1	1

	Mixed Director	TV Shows Count	Netflix	Hulu	Disney+
5	Fabien Beziat,Hugues Nancy	2	2	0	0
0	Aaron Basch,Trevor Morris,Chris Olivas,Peter S...	1	0	1	0
16	Paul Stodolny,Ricardo Curtis,Steve Martino,Mik...	1	0	0	1
29	Volker Arzt,Angelika Sigl	1	1	0	0
28	Victor Cook,Kevin Altieri,Alan Caldwell,Victor...	1	1	0	0

	Mixed Director	TV Shows Count	Netflix	Prime Video
5	Fabien Beziat,Hugues Nancy	2	2	0
15	Nikolay Kozlov,Aleksandr Lyutkevich	1	1	0
2	Bruno Mattei,Claudio Fragasso	1	0	1
3	Daniel Zuckerbrot,Donna Zuckerbrot	1	0	1
4	David Belton,Andy Byatt	1	0	1
6	Francesco Manfio,Sergio Manfio	1	0	1
7	Gary Howsam,Mike Smith,John Paul Tremblay,Robb...	1	1	0
8	Jamie Badminton,Rufus Blacklock	1	0	1
9	Josh Wakely,Pablo De La Torre	1	1	0
10	José Luis Gutiérrez Rojas,Leopoldo Gutiérrez	1	0	1

	Mixed Director	TV Shows Count	Netflix	Hulu	Disney+
0	Aaron Basch,Trevor Morris,Chris Olivas,Peter S...	1	0	1	0
1	Nelson Boles,Raymie Muzquiz	1	0	1	0
2	Fabien Beziat,Hugues Nancy	2	2	0	0
3	Paul Stodolny,Ricardo Curtis,Steve Martino,Mik...	1	0	0	1
4	Volker Arzt,Angelika Sigl	1	1	0	0

	Mixed Director	TV Shows Count	Hulu	Disney+
0	William Beaudine,Wilfred Jackson	1	0	1
1	Paul Stodolny,Ricardo Curtis,Steve Martino,Mik...	1	0	1
2	Sol Choi,Alfred Gimeno	1	0	1
3	Robert Hughes,Sue Perrotto	1	0	1
4	Aaron Basch,Trevor Morris,Chris Olivas,Peter S...	1	1	0